Merge branch 'for-linus' of git://oss.sgi.com/xfs/xfs

* 'for-linus' of git://oss.sgi.com/xfs/xfs:
  xfs: improve xfs_isilocked
  xfs: skip writeback from reclaim context
  xfs: remove done roadmap item from xfs-delayed-logging-design.txt
  xfs: fix race in inode cluster freeing failing to stale inodes
  xfs: fix access to upper inodes without inode64
  xfs: fix might_sleep() warning when initialising per-ag tree
  fs/xfs/quota: Add missing mutex_unlock
  xfs: remove duplicated #include
  xfs: convert more trace events to DEFINE_EVENT
  xfs: xfs_trace.c: remove duplicated #include
  xfs: Check new inode size is OK before preallocating
  xfs: clean up xlog_align
  xfs: cleanup log reservation calculactions
  xfs: be more explicit if RT mount fails due to config
  xfs: replace E2BIG with EFBIG where appropriate

17 files changed, 736 insertions, 793 deletions

diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 089eaca860b4..a0fa3bf0d1bb 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -1333,6 +1333,21 @@ xfs_vm_writepage(
 	trace_xfs_writepage(inode, page, 0);
 
 	/*
+	 * Refuse to write the page out if we are called from reclaim context.
+	 *
+	 * This is primarily to avoid stack overflows when called from deep
+	 * used stacks in random callers for direct reclaim, but disabling
+	 * reclaim for kswap is a nice side-effect as kswapd causes rather
+	 * suboptimal I/O patters, too.
+	 *
+	 * This should really be done by the core VM, but until that happens
+	 * filesystems like XFS, btrfs and ext4 have to take care of this
+	 * by themselves.
+	 */
+	if (current->flags & PF_MEMALLOC)
+		goto out_fail;
+
+	/*
 	 * We need a transaction if:
 	 *  1. There are delalloc buffers on the page
 	 *  2. The page is uptodate and we have unmapped buffers
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index 9c8019c78c92..44f0b2de153e 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -585,11 +585,20 @@ xfs_vn_fallocate(
 	bf.l_len = len;
 
 	xfs_ilock(ip, XFS_IOLOCK_EXCL);
+
+	/* check the new inode size is valid before allocating */
+	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
+	    offset + len > i_size_read(inode)) {
+		new_size = offset + len;
+		error = inode_newsize_ok(inode, new_size);
+		if (error)
+			goto out_unlock;
+	}
+
 	error = -xfs_change_file_space(ip, XFS_IOC_RESVSP, &bf,
 				       0, XFS_ATTR_NOLOCK);
-	if (!error && !(mode & FALLOC_FL_KEEP_SIZE) &&
-	    offset + len > i_size_read(inode))
-		new_size = offset + len;
+	if (error)
+		goto out_unlock;
 
 	/* Change file size if needed */
 	if (new_size) {
@@ -600,6 +609,7 @@ xfs_vn_fallocate(
 		error = -xfs_setattr(ip, &iattr, XFS_ATTR_NOLOCK);
 	}
 
+out_unlock:
 	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 out_error:
 	return error;
diff --git a/fs/xfs/linux-2.6/xfs_quotaops.c b/fs/xfs/linux-2.6/xfs_quotaops.c
index 9ac8aea91529..067cafbfc635 100644
--- a/fs/xfs/linux-2.6/xfs_quotaops.c
+++ b/fs/xfs/linux-2.6/xfs_quotaops.c
@@ -23,7 +23,6 @@
 #include "xfs_ag.h"
 #include "xfs_mount.h"
 #include "xfs_quota.h"
-#include "xfs_log.h"
 #include "xfs_trans.h"
 #include "xfs_bmap_btree.h"
 #include "xfs_inode.h"
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index 3884e20bc14e..ef7f0218bccb 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -164,10 +164,6 @@ xfs_inode_ag_iterator(
 		struct xfs_perag	*pag;
 
 		pag = xfs_perag_get(mp, ag);
-		if (!pag->pag_ici_init) {
-			xfs_perag_put(pag);
-			continue;
-		}
 		error = xfs_inode_ag_walk(mp, pag, execute, flags, tag,
 						exclusive, &nr);
 		xfs_perag_put(pag);
@@ -867,12 +863,7 @@ xfs_reclaim_inode_shrink(
 	down_read(&xfs_mount_list_lock);
 	list_for_each_entry(mp, &xfs_mount_list, m_mplist) {
 		for (ag = 0; ag < mp->m_sb.sb_agcount; ag++) {
-
 			pag = xfs_perag_get(mp, ag);
-			if (!pag->pag_ici_init) {
-				xfs_perag_put(pag);
-				continue;
-			}
 			reclaimable += pag->pag_ici_reclaimable;
 			xfs_perag_put(pag);
 		}
diff --git a/fs/xfs/linux-2.6/xfs_trace.c b/fs/xfs/linux-2.6/xfs_trace.c
index 207fa77f63ae..d12be8470cba 100644
--- a/fs/xfs/linux-2.6/xfs_trace.c
+++ b/fs/xfs/linux-2.6/xfs_trace.c
@@ -50,7 +50,6 @@
 #include "quota/xfs_dquot_item.h"
 #include "quota/xfs_dquot.h"
 #include "xfs_log_recover.h"
-#include "xfs_buf_item.h"
 #include "xfs_inode_item.h"
 
 /*
diff --git a/fs/xfs/linux-2.6/xfs_trace.h b/fs/xfs/linux-2.6/xfs_trace.h
index ff6bc797baf2..73d5aa117384 100644
--- a/fs/xfs/linux-2.6/xfs_trace.h
+++ b/fs/xfs/linux-2.6/xfs_trace.h
@@ -82,33 +82,6 @@ DECLARE_EVENT_CLASS(xfs_attr_list_class,
 	)
 )
 
-#define DEFINE_PERAG_REF_EVENT(name) \
-TRACE_EVENT(name, \
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, int refcount, \
-		 unsigned long caller_ip), \
-	TP_ARGS(mp, agno, refcount, caller_ip), \
-	TP_STRUCT__entry( \
-		__field(dev_t, dev) \
-		__field(xfs_agnumber_t, agno) \
-		__field(int, refcount) \
-		__field(unsigned long, caller_ip) \
-	), \
-	TP_fast_assign( \
-		__entry->dev = mp->m_super->s_dev; \
-		__entry->agno = agno; \
-		__entry->refcount = refcount; \
-		__entry->caller_ip = caller_ip; \
-	), \
-	TP_printk("dev %d:%d agno %u refcount %d caller %pf", \
-		  MAJOR(__entry->dev), MINOR(__entry->dev), \
-		  __entry->agno, \
-		  __entry->refcount, \
-		  (char *)__entry->caller_ip) \
-);
-
-DEFINE_PERAG_REF_EVENT(xfs_perag_get)
-DEFINE_PERAG_REF_EVENT(xfs_perag_put)
-
 #define DEFINE_ATTR_LIST_EVENT(name) \
 DEFINE_EVENT(xfs_attr_list_class, name, \
 	TP_PROTO(struct xfs_attr_list_context *ctx), \
@@ -122,6 +95,37 @@ DEFINE_ATTR_LIST_EVENT(xfs_attr_list_add);
 DEFINE_ATTR_LIST_EVENT(xfs_attr_list_wrong_blk);
 DEFINE_ATTR_LIST_EVENT(xfs_attr_list_notfound);
 
+DECLARE_EVENT_CLASS(xfs_perag_class,
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, int refcount,
+		 unsigned long caller_ip),
+	TP_ARGS(mp, agno, refcount, caller_ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(int, refcount)
+		__field(unsigned long, caller_ip)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->agno = agno;
+		__entry->refcount = refcount;
+		__entry->caller_ip = caller_ip;
+	),
+	TP_printk("dev %d:%d agno %u refcount %d caller %pf",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->refcount,
+		  (char *)__entry->caller_ip)
+);
+
+#define DEFINE_PERAG_REF_EVENT(name)	\
+DEFINE_EVENT(xfs_perag_class, name,	\
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, int refcount,	\
+		 unsigned long caller_ip),					\
+	TP_ARGS(mp, agno, refcount, caller_ip))
+DEFINE_PERAG_REF_EVENT(xfs_perag_get);
+DEFINE_PERAG_REF_EVENT(xfs_perag_put);
+
 TRACE_EVENT(xfs_attr_list_node_descend,
 	TP_PROTO(struct xfs_attr_list_context *ctx,
 		 struct xfs_da_node_entry *btree),
@@ -775,165 +779,181 @@ DEFINE_LOGGRANT_EVENT(xfs_log_ungrant_enter);
 DEFINE_LOGGRANT_EVENT(xfs_log_ungrant_exit);
 DEFINE_LOGGRANT_EVENT(xfs_log_ungrant_sub);
 
-#define DEFINE_RW_EVENT(name) \
-TRACE_EVENT(name, \
-	TP_PROTO(struct xfs_inode *ip, size_t count, loff_t offset, int flags), \
-	TP_ARGS(ip, count, offset, flags), \
-	TP_STRUCT__entry( \
-		__field(dev_t, dev) \
-		__field(xfs_ino_t, ino) \
-		__field(xfs_fsize_t, size) \
-		__field(xfs_fsize_t, new_size) \
-		__field(loff_t, offset) \
-		__field(size_t, count) \
-		__field(int, flags) \
-	), \
-	TP_fast_assign( \
-		__entry->dev = VFS_I(ip)->i_sb->s_dev; \
-		__entry->ino = ip->i_ino; \
-		__entry->size = ip->i_d.di_size; \
-		__entry->new_size = ip->i_new_size; \
-		__entry->offset = offset; \
-		__entry->count = count; \
-		__entry->flags = flags; \
-	), \
-	TP_printk("dev %d:%d ino 0x%llx size 0x%llx new_size 0x%llx " \
-		  "offset 0x%llx count 0x%zx ioflags %s", \
-		  MAJOR(__entry->dev), MINOR(__entry->dev), \
-		  __entry->ino, \
-		  __entry->size, \
-		  __entry->new_size, \
-		  __entry->offset, \
-		  __entry->count, \
-		  __print_flags(__entry->flags, "|", XFS_IO_FLAGS)) \
+DECLARE_EVENT_CLASS(xfs_file_class,
+	TP_PROTO(struct xfs_inode *ip, size_t count, loff_t offset, int flags),
+	TP_ARGS(ip, count, offset, flags),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(xfs_fsize_t, size)
+		__field(xfs_fsize_t, new_size)
+		__field(loff_t, offset)
+		__field(size_t, count)
+		__field(int, flags)
+	),
+	TP_fast_assign(
+		__entry->dev = VFS_I(ip)->i_sb->s_dev;
+		__entry->ino = ip->i_ino;
+		__entry->size = ip->i_d.di_size;
+		__entry->new_size = ip->i_new_size;
+		__entry->offset = offset;
+		__entry->count = count;
+		__entry->flags = flags;
+	),
+	TP_printk("dev %d:%d ino 0x%llx size 0x%llx new_size 0x%llx "
+		  "offset 0x%llx count 0x%zx ioflags %s",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->size,
+		  __entry->new_size,
+		  __entry->offset,
+		  __entry->count,
+		  __print_flags(__entry->flags, "|", XFS_IO_FLAGS))
 )
+
+#define DEFINE_RW_EVENT(name)		\
+DEFINE_EVENT(xfs_file_class, name,	\
+	TP_PROTO(struct xfs_inode *ip, size_t count, loff_t offset, int flags),	\
+	TP_ARGS(ip, count, offset, flags))
 DEFINE_RW_EVENT(xfs_file_read);
 DEFINE_RW_EVENT(xfs_file_buffered_write);
 DEFINE_RW_EVENT(xfs_file_direct_write);
 DEFINE_RW_EVENT(xfs_file_splice_read);
 DEFINE_RW_EVENT(xfs_file_splice_write);
 
-
-#define DEFINE_PAGE_EVENT(name) \
-TRACE_EVENT(name, \
-	TP_PROTO(struct inode *inode, struct page *page, unsigned long off), \
-	TP_ARGS(inode, page, off), \
-	TP_STRUCT__entry( \
-		__field(dev_t, dev) \
-		__field(xfs_ino_t, ino) \
-		__field(pgoff_t, pgoff) \
-		__field(loff_t, size) \
-		__field(unsigned long, offset) \
-		__field(int, delalloc) \
-		__field(int, unmapped) \
-		__field(int, unwritten) \
-	), \
-	TP_fast_assign( \
-		int delalloc = -1, unmapped = -1, unwritten = -1; \
-	\
-		if (page_has_buffers(page)) \
-			xfs_count_page_state(page, &delalloc, \
-					     &unmapped, &unwritten); \
-		__entry->dev = inode->i_sb->s_dev; \
-		__entry->ino = XFS_I(inode)->i_ino; \
-		__entry->pgoff = page_offset(page); \
-		__entry->size = i_size_read(inode); \
-		__entry->offset = off; \
-		__entry->delalloc = delalloc; \
-		__entry->unmapped = unmapped; \
-		__entry->unwritten = unwritten; \
-	), \
-	TP_printk("dev %d:%d ino 0x%llx pgoff 0x%lx size 0x%llx offset %lx " \
-		  "delalloc %d unmapped %d unwritten %d", \
-		  MAJOR(__entry->dev), MINOR(__entry->dev), \
-		  __entry->ino, \
-		  __entry->pgoff, \
-		  __entry->size, \
-		  __entry->offset, \
-		  __entry->delalloc, \
-		  __entry->unmapped, \
-		  __entry->unwritten) \
+DECLARE_EVENT_CLASS(xfs_page_class,
+	TP_PROTO(struct inode *inode, struct page *page, unsigned long off),
+	TP_ARGS(inode, page, off),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(pgoff_t, pgoff)
+		__field(loff_t, size)
+		__field(unsigned long, offset)
+		__field(int, delalloc)
+		__field(int, unmapped)
+		__field(int, unwritten)
+	),
+	TP_fast_assign(
+		int delalloc = -1, unmapped = -1, unwritten = -1;
+
+		if (page_has_buffers(page))
+			xfs_count_page_state(page, &delalloc,
+					     &unmapped, &unwritten);
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = XFS_I(inode)->i_ino;
+		__entry->pgoff = page_offset(page);
+		__entry->size = i_size_read(inode);
+		__entry->offset = off;
+		__entry->delalloc = delalloc;
+		__entry->unmapped = unmapped;
+		__entry->unwritten = unwritten;
+	),
+	TP_printk("dev %d:%d ino 0x%llx pgoff 0x%lx size 0x%llx offset %lx "
+		  "delalloc %d unmapped %d unwritten %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->pgoff,
+		  __entry->size,
+		  __entry->offset,
+		  __entry->delalloc,
+		  __entry->unmapped,
+		  __entry->unwritten)
 )
+
+#define DEFINE_PAGE_EVENT(name)		\
+DEFINE_EVENT(xfs_page_class, name,	\
+	TP_PROTO(struct inode *inode, struct page *page, unsigned long off),	\
+	TP_ARGS(inode, page, off))
 DEFINE_PAGE_EVENT(xfs_writepage);
 DEFINE_PAGE_EVENT(xfs_releasepage);
 DEFINE_PAGE_EVENT(xfs_invalidatepage);
 
-#define DEFINE_IOMAP_EVENT(name) \
-TRACE_EVENT(name, \
-	TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count, \
-		 int flags, struct xfs_bmbt_irec *irec), \
-	TP_ARGS(ip, offset, count, flags, irec), \
-	TP_STRUCT__entry( \
-		__field(dev_t, dev) \
-		__field(xfs_ino_t, ino) \
-		__field(loff_t, size) \
-		__field(loff_t, new_size) \
-		__field(loff_t, offset) \
-		__field(size_t, count) \
-		__field(int, flags) \
-		__field(xfs_fileoff_t, startoff) \
-		__field(xfs_fsblock_t, startblock) \
-		__field(xfs_filblks_t, blockcount) \
-	), \
-	TP_fast_assign( \
-		__entry->dev = VFS_I(ip)->i_sb->s_dev; \
-		__entry->ino = ip->i_ino; \
-		__entry->size = ip->i_d.di_size; \
-		__entry->new_size = ip->i_new_size; \
-		__entry->offset = offset; \
-		__entry->count = count; \
-		__entry->flags = flags; \
-		__entry->startoff = irec ? irec->br_startoff : 0; \
-		__entry->startblock = irec ? irec->br_startblock : 0; \
-		__entry->blockcount = irec ? irec->br_blockcount : 0; \
-	), \
-	TP_printk("dev %d:%d ino 0x%llx size 0x%llx new_size 0x%llx " \
-		  "offset 0x%llx count %zd flags %s " \
-		  "startoff 0x%llx startblock %lld blockcount 0x%llx", \
-		  MAJOR(__entry->dev), MINOR(__entry->dev), \
-		  __entry->ino, \
-		  __entry->size, \
-		  __entry->new_size, \
-		  __entry->offset, \
-		  __entry->count, \
-		  __print_flags(__entry->flags, "|", BMAPI_FLAGS), \
-		  __entry->startoff, \
-		  (__int64_t)__entry->startblock, \
-		  __entry->blockcount) \
+DECLARE_EVENT_CLASS(xfs_iomap_class,
+	TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count,
+		 int flags, struct xfs_bmbt_irec *irec),
+	TP_ARGS(ip, offset, count, flags, irec),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(loff_t, size)
+		__field(loff_t, new_size)
+		__field(loff_t, offset)
+		__field(size_t, count)
+		__field(int, flags)
+		__field(xfs_fileoff_t, startoff)
+		__field(xfs_fsblock_t, startblock)
+		__field(xfs_filblks_t, blockcount)
+	),
+	TP_fast_assign(
+		__entry->dev = VFS_I(ip)->i_sb->s_dev;
+		__entry->ino = ip->i_ino;
+		__entry->size = ip->i_d.di_size;
+		__entry->new_size = ip->i_new_size;
+		__entry->offset = offset;
+		__entry->count = count;
+		__entry->flags = flags;
+		__entry->startoff = irec ? irec->br_startoff : 0;
+		__entry->startblock = irec ? irec->br_startblock : 0;
+		__entry->blockcount = irec ? irec->br_blockcount : 0;
+	),
+	TP_printk("dev %d:%d ino 0x%llx size 0x%llx new_size 0x%llx "
+		  "offset 0x%llx count %zd flags %s "
+		  "startoff 0x%llx startblock %lld blockcount 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->size,
+		  __entry->new_size,
+		  __entry->offset,
+		  __entry->count,
+		  __print_flags(__entry->flags, "|", BMAPI_FLAGS),
+		  __entry->startoff,
+		  (__int64_t)__entry->startblock,
+		  __entry->blockcount)
 )
+
+#define DEFINE_IOMAP_EVENT(name)	\
+DEFINE_EVENT(xfs_iomap_class, name,	\
+	TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count,	\
+		 int flags, struct xfs_bmbt_irec *irec),		\
+	TP_ARGS(ip, offset, count, flags, irec))
 DEFINE_IOMAP_EVENT(xfs_iomap_enter);
 DEFINE_IOMAP_EVENT(xfs_iomap_found);
 DEFINE_IOMAP_EVENT(xfs_iomap_alloc);
 
-#define DEFINE_SIMPLE_IO_EVENT(name) \
-TRACE_EVENT(name, \
-	TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count), \
-	TP_ARGS(ip, offset, count), \
-	TP_STRUCT__entry( \
-		__field(dev_t, dev) \
-		__field(xfs_ino_t, ino) \
-		__field(loff_t, size) \
-		__field(loff_t, new_size) \
-		__field(loff_t, offset) \
-		__field(size_t, count) \
-	), \
-	TP_fast_assign( \
-		__entry->dev = VFS_I(ip)->i_sb->s_dev; \
-		__entry->ino = ip->i_ino; \
-		__entry->size = ip->i_d.di_size; \
-		__entry->new_size = ip->i_new_size; \
-		__entry->offset = offset; \
-		__entry->count = count; \
-	), \
-	TP_printk("dev %d:%d ino 0x%llx size 0x%llx new_size 0x%llx " \
-		  "offset 0x%llx count %zd", \
-		  MAJOR(__entry->dev), MINOR(__entry->dev), \
-		  __entry->ino, \
-		  __entry->size, \
-		  __entry->new_size, \
-		  __entry->offset, \
-		  __entry->count) \
+DECLARE_EVENT_CLASS(xfs_simple_io_class,
+	TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count),
+	TP_ARGS(ip, offset, count),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(loff_t, size)
+		__field(loff_t, new_size)
+		__field(loff_t, offset)
+		__field(size_t, count)
+	),
+	TP_fast_assign(
+		__entry->dev = VFS_I(ip)->i_sb->s_dev;
+		__entry->ino = ip->i_ino;
+		__entry->size = ip->i_d.di_size;
+		__entry->new_size = ip->i_new_size;
+		__entry->offset = offset;
+		__entry->count = count;
+	),
+	TP_printk("dev %d:%d ino 0x%llx size 0x%llx new_size 0x%llx "
+		  "offset 0x%llx count %zd",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->size,
+		  __entry->new_size,
+		  __entry->offset,
+		  __entry->count)
 );
+
+#define DEFINE_SIMPLE_IO_EVENT(name)	\
+DEFINE_EVENT(xfs_simple_io_class, name,	\
+	TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count),	\
+	TP_ARGS(ip, offset, count))
 DEFINE_SIMPLE_IO_EVENT(xfs_delalloc_enospc);
 DEFINE_SIMPLE_IO_EVENT(xfs_unwritten_convert);
 
diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c
index 38e764146644..2d8b7bc792c9 100644
--- a/fs/xfs/quota/xfs_qm.c
+++ b/fs/xfs/quota/xfs_qm.c
@@ -249,8 +249,10 @@ xfs_qm_hold_quotafs_ref(
 
 	if (!xfs_Gqm) {
 		xfs_Gqm = xfs_Gqm_init();
-		if (!xfs_Gqm)
+		if (!xfs_Gqm) {
+			mutex_unlock(&xfs_Gqm_lock);
 			return ENOMEM;
+		}
 	}
 
 	/*
diff --git a/fs/xfs/xfs_ag.h b/fs/xfs/xfs_ag.h
index 401f364ad36c..4917d4eed4ed 100644
--- a/fs/xfs/xfs_ag.h
+++ b/fs/xfs/xfs_ag.h
@@ -227,7 +227,6 @@ typedef struct xfs_perag {
 
 	atomic_t        pagf_fstrms;    /* # of filestreams active in this AG */
 
-	int		pag_ici_init;	/* incore inode cache initialised */
 	rwlock_t	pag_ici_lock;	/* incore inode lock */
 	struct radix_tree_root pag_ici_root;	/* incore inode cache root */
 	int		pag_ici_reclaimable;	/* reclaimable inodes */
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index 6845db90818f..75df75f43d48 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -382,9 +382,6 @@ xfs_iget(
 
 	/* get the perag structure and ensure that it's inode capable */
 	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ino));
-	if (!pag->pagi_inodeok)
-		return EINVAL;
-	ASSERT(pag->pag_ici_init);
 	agino = XFS_INO_TO_AGINO(mp, ino);
 
 again:
@@ -744,30 +741,24 @@ xfs_ilock_demote(
 }
 
 #ifdef DEBUG
-/*
- * Debug-only routine, without additional rw_semaphore APIs, we can
- * now only answer requests regarding whether we hold the lock for write
- * (reader state is outside our visibility, we only track writer state).
- *
- * Note: this means !xfs_isilocked would give false positives, so don't do that.
- */
 int
 xfs_isilocked(
 	xfs_inode_t		*ip,
 	uint			lock_flags)
 {
-	if ((lock_flags & (XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)) ==
-			XFS_ILOCK_EXCL) {
-		if (!ip->i_lock.mr_writer)
-			return 0;
+	if (lock_flags & (XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)) {
+		if (!(lock_flags & XFS_ILOCK_SHARED))
+			return !!ip->i_lock.mr_writer;
+		return rwsem_is_locked(&ip->i_lock.mr_lock);
 	}
 
-	if ((lock_flags & (XFS_IOLOCK_EXCL|XFS_IOLOCK_SHARED)) ==
-			XFS_IOLOCK_EXCL) {
-		if (!ip->i_iolock.mr_writer)
-			return 0;
+	if (lock_flags & (XFS_IOLOCK_EXCL|XFS_IOLOCK_SHARED)) {
+		if (!(lock_flags & XFS_IOLOCK_SHARED))
+			return !!ip->i_iolock.mr_writer;
+		return rwsem_is_locked(&ip->i_iolock.mr_lock);
 	}
 
-	return 1;
+	ASSERT(0);
+	return 0;
 }
 #endif
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 8cd6e8d8fe9c..d53c39de7d05 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1940,10 +1940,10 @@ xfs_ifree_cluster(
 	int			blks_per_cluster;
 	int			nbufs;
 	int			ninodes;
-	int			i, j, found, pre_flushed;
+	int			i, j;
 	xfs_daddr_t		blkno;
 	xfs_buf_t		*bp;
-	xfs_inode_t		*ip, **ip_found;
+	xfs_inode_t		*ip;
 	xfs_inode_log_item_t	*iip;
 	xfs_log_item_t		*lip;
 	struct xfs_perag	*pag;
@@ -1960,114 +1960,97 @@ xfs_ifree_cluster(
 		nbufs = XFS_IALLOC_BLOCKS(mp) / blks_per_cluster;
 	}
 
-	ip_found = kmem_alloc(ninodes * sizeof(xfs_inode_t *), KM_NOFS);
-
 	for (j = 0; j < nbufs; j++, inum += ninodes) {
+		int	found = 0;
+
 		blkno = XFS_AGB_TO_DADDR(mp, XFS_INO_TO_AGNO(mp, inum),
 					 XFS_INO_TO_AGBNO(mp, inum));
 
+		/*
+		 * We obtain and lock the backing buffer first in the process
+		 * here, as we have to ensure that any dirty inode that we
+		 * can't get the flush lock on is attached to the buffer.
+		 * If we scan the in-memory inodes first, then buffer IO can
+		 * complete before we get a lock on it, and hence we may fail
+		 * to mark all the active inodes on the buffer stale.
+		 */
+		bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno,
+					mp->m_bsize * blks_per_cluster,
+					XBF_LOCK);
+
+		/*
+		 * Walk the inodes already attached to the buffer and mark them
+		 * stale. These will all have the flush locks held, so an
+		 * in-memory inode walk can't lock them.
+		 */
+		lip = XFS_BUF_FSPRIVATE(bp, xfs_log_item_t *);
+		while (lip) {
+			if (lip->li_type == XFS_LI_INODE) {
+				iip = (xfs_inode_log_item_t *)lip;
+				ASSERT(iip->ili_logged == 1);
+				lip->li_cb = (void(*)(xfs_buf_t*,xfs_log_item_t*)) xfs_istale_done;
+				xfs_trans_ail_copy_lsn(mp->m_ail,
+							&iip->ili_flush_lsn,
+							&iip->ili_item.li_lsn);
+				xfs_iflags_set(iip->ili_inode, XFS_ISTALE);
+				found++;
+			}
+			lip = lip->li_bio_list;
+		}
 
 		/*
-		 * Look for each inode in memory and attempt to lock it,
-		 * we can be racing with flush and tail pushing here.
-		 * any inode we get the locks on, add to an array of
-		 * inode items to process later.
+		 * For each inode in memory attempt to add it to the inode
+		 * buffer and set it up for being staled on buffer IO
+		 * completion.  This is safe as we've locked out tail pushing
+		 * and flushing by locking the buffer.
 		 *
-		 * The get the buffer lock, we could beat a flush
-		 * or tail pushing thread to the lock here, in which
-		 * case they will go looking for the inode buffer
-		 * and fail, we need some other form of interlock
-		 * here.
+		 * We have already marked every inode that was part of a
+		 * transaction stale above, which means there is no point in
+		 * even trying to lock them.
 		 */
-		found = 0;
 		for (i = 0; i < ninodes; i++) {
 			read_lock(&pag->pag_ici_lock);
 			ip = radix_tree_lookup(&pag->pag_ici_root,
 					XFS_INO_TO_AGINO(mp, (inum + i)));
 
-			/* Inode not in memory or we found it already,
-			 * nothing to do
-			 */
+			/* Inode not in memory or stale, nothing to do */
 			if (!ip || xfs_iflags_test(ip, XFS_ISTALE)) {
 				read_unlock(&pag->pag_ici_lock);
 				continue;
 			}
 
-			if (xfs_inode_clean(ip)) {
-				read_unlock(&pag->pag_ici_lock);
-				continue;
-			}
-
-			/* If we can get the locks then add it to the
-			 * list, otherwise by the time we get the bp lock
-			 * below it will already be attached to the
-			 * inode buffer.
-			 */
-
-			/* This inode will already be locked - by us, lets
-			 * keep it that way.
-			 */
-
-			if (ip == free_ip) {
-				if (xfs_iflock_nowait(ip)) {
-					xfs_iflags_set(ip, XFS_ISTALE);
-					if (xfs_inode_clean(ip)) {
-						xfs_ifunlock(ip);
-					} else {
-						ip_found[found++] = ip;
-					}
-				}
+			/* don't try to lock/unlock the current inode */
+			if (ip != free_ip &&
+			    !xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
 				read_unlock(&pag->pag_ici_lock);
 				continue;
 			}
+			read_unlock(&pag->pag_ici_lock);
 
-			if (xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
-				if (xfs_iflock_nowait(ip)) {
-					xfs_iflags_set(ip, XFS_ISTALE);
-
-					if (xfs_inode_clean(ip)) {
-						xfs_ifunlock(ip);
-						xfs_iunlock(ip, XFS_ILOCK_EXCL);
-					} else {
-						ip_found[found++] = ip;
-					}
-				} else {
+			if (!xfs_iflock_nowait(ip)) {
+				if (ip != free_ip)
 					xfs_iunlock(ip, XFS_ILOCK_EXCL);
-				}
+				continue;
 			}
-			read_unlock(&pag->pag_ici_lock);
-		}
 
-		bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno, 
-					mp->m_bsize * blks_per_cluster,
-					XBF_LOCK);
-
-		pre_flushed = 0;
-		lip = XFS_BUF_FSPRIVATE(bp, xfs_log_item_t *);
-		while (lip) {
-			if (lip->li_type == XFS_LI_INODE) {
-				iip = (xfs_inode_log_item_t *)lip;
-				ASSERT(iip->ili_logged == 1);
-				lip->li_cb = (void(*)(xfs_buf_t*,xfs_log_item_t*)) xfs_istale_done;
-				xfs_trans_ail_copy_lsn(mp->m_ail,
-							&iip->ili_flush_lsn,
-							&iip->ili_item.li_lsn);
-				xfs_iflags_set(iip->ili_inode, XFS_ISTALE);
-				pre_flushed++;
+			xfs_iflags_set(ip, XFS_ISTALE);
+			if (xfs_inode_clean(ip)) {
+				ASSERT(ip != free_ip);
+				xfs_ifunlock(ip);
+				xfs_iunlock(ip, XFS_ILOCK_EXCL);
+				continue;
 			}
-			lip = lip->li_bio_list;
-		}
 
-		for (i = 0; i < found; i++) {
-			ip = ip_found[i];
 			iip = ip->i_itemp;
-
 			if (!iip) {
+				/* inode with unlogged changes only */
+				ASSERT(ip != free_ip);
 				ip->i_update_core = 0;
 				xfs_ifunlock(ip);
 				xfs_iunlock(ip, XFS_ILOCK_EXCL);
 				continue;
 			}
+			found++;
 
 			iip->ili_last_fields = iip->ili_format.ilf_fields;
 			iip->ili_format.ilf_fields = 0;
@@ -2078,17 +2061,16 @@ xfs_ifree_cluster(
 			xfs_buf_attach_iodone(bp,
 				(void(*)(xfs_buf_t*,xfs_log_item_t*))
 				xfs_istale_done, (xfs_log_item_t *)iip);
-			if (ip != free_ip) {
+
+			if (ip != free_ip)
 				xfs_iunlock(ip, XFS_ILOCK_EXCL);
-			}
 		}
 
-		if (found || pre_flushed)
+		if (found)
 			xfs_trans_stale_inode_buf(tp, bp);
 		xfs_trans_binval(tp, bp);
 	}
 
-	kmem_free(ip_found);
 	xfs_perag_put(pag);
 }
 
@@ -2649,8 +2631,6 @@ xfs_iflush_cluster(
 	int			i;
 
 	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
-	ASSERT(pag->pagi_inodeok);
-	ASSERT(pag->pag_ici_init);
 
 	inodes_per_cluster = XFS_INODE_CLUSTER_SIZE(mp) >> mp->m_sb.sb_inodelog;
 	ilist_size = inodes_per_cluster * sizeof(xfs_inode_t *);
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 14a69aec2c0b..ed0684cc50ee 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -132,15 +132,10 @@ xlog_align(
 	int		nbblks,
 	xfs_buf_t	*bp)
 {
-	xfs_daddr_t	offset;
-	xfs_caddr_t	ptr;
+	xfs_daddr_t	offset = blk_no & ((xfs_daddr_t)log->l_sectBBsize - 1);
 
-	offset = blk_no & ((xfs_daddr_t) log->l_sectBBsize - 1);
-	ptr = XFS_BUF_PTR(bp) + BBTOB(offset);
-
-	ASSERT(ptr + BBTOB(nbblks) <= XFS_BUF_PTR(bp) + XFS_BUF_SIZE(bp));
-
-	return ptr;
+	ASSERT(BBTOB(offset + nbblks) <= XFS_BUF_SIZE(bp));
+	return XFS_BUF_PTR(bp) + BBTOB(offset);
 }
 
 
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index d7bf38c8cd1c..d59f4e8bedcf 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -268,10 +268,10 @@ xfs_sb_validate_fsb_count(
 
 #if XFS_BIG_BLKNOS     /* Limited by ULONG_MAX of page cache index */
 	if (nblocks >> (PAGE_CACHE_SHIFT - sbp->sb_blocklog) > ULONG_MAX)
-		return E2BIG;
+		return EFBIG;
 #else                  /* Limited by UINT_MAX of sectors */
 	if (nblocks << (sbp->sb_blocklog - BBSHIFT) > UINT_MAX)
-		return E2BIG;
+		return EFBIG;
 #endif
 	return 0;
 }
@@ -393,7 +393,7 @@ xfs_mount_validate_sb(
 	    xfs_sb_validate_fsb_count(sbp, sbp->sb_rblocks)) {
 		xfs_fs_mount_cmn_err(flags,
 			"file system too large to be mounted on this system.");
-		return XFS_ERROR(E2BIG);
+		return XFS_ERROR(EFBIG);
 	}
 
 	if (unlikely(sbp->sb_inprogress)) {
@@ -413,17 +413,6 @@ xfs_mount_validate_sb(
 	return 0;
 }
 
-STATIC void
-xfs_initialize_perag_icache(
-	xfs_perag_t	*pag)
-{
-	if (!pag->pag_ici_init) {
-		rwlock_init(&pag->pag_ici_lock);
-		INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC);
-		pag->pag_ici_init = 1;
-	}
-}
-
 int
 xfs_initialize_perag(
 	xfs_mount_t	*mp,
@@ -436,13 +425,8 @@ xfs_initialize_perag(
 	xfs_agino_t	agino;
 	xfs_ino_t	ino;
 	xfs_sb_t	*sbp = &mp->m_sb;
-	xfs_ino_t	max_inum = XFS_MAXINUMBER_32;
 	int		error = -ENOMEM;
 
-	/* Check to see if the filesystem can overflow 32 bit inodes */
-	agino = XFS_OFFBNO_TO_AGINO(mp, sbp->sb_agblocks - 1, 0);
-	ino = XFS_AGINO_TO_INO(mp, agcount - 1, agino);
-
 	/*
 	 * Walk the current per-ag tree so we don't try to initialise AGs
 	 * that already exist (growfs case). Allocate and insert all the
@@ -456,11 +440,18 @@ xfs_initialize_perag(
 		}
 		if (!first_initialised)
 			first_initialised = index;
+
 		pag = kmem_zalloc(sizeof(*pag), KM_MAYFAIL);
 		if (!pag)
 			goto out_unwind;
+		pag->pag_agno = index;
+		pag->pag_mount = mp;
+		rwlock_init(&pag->pag_ici_lock);
+		INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC);
+
 		if (radix_tree_preload(GFP_NOFS))
 			goto out_unwind;
+
 		spin_lock(&mp->m_perag_lock);
 		if (radix_tree_i